Basic Statistics - Learn Types, Terms, Applications, and Formulas

Currently, in college, you will be familiar with data, variables, population, samples, averages, standard deviations, and medians. All of these terms you are familiar with the turn out to be included in the discussion of basic statistics. RODA Statistics will explain this material, including its types, general terms, and formulas used.

License

How to use my images

Photographer: Andhi Setya Hermawan

Copyright: Citra Ayumsari

Credit: RODA Statistics

Understanding Basic Statistics

The first discussion that Citra will explain is the meaning of statistics. Have you ever heard of the words statistics and statistics?

Many call statistics with statistics, even though these two words have different meanings. If statistics are processed, data analysis results from certain calculations.

Statistics is a branch of science that will generally be in contact with data collection, processing, analysis, and interpretation, which will later be used to carry out preventive actions or make predictions. So in statistics material, you will learn how to collect data, how process data, and how to analyze and to interpret data.

In basic statistics, students generally learn about the tendency of data centring, how to find the mean, median, and mode values, locate data, measure data deviations, and measure data distribution. Citra will explain all this in the material this time.

Types of Statistics

In statistics, it turns out that there is not only one type of statistics. There are several types of statistics that are distinguished based on several categories. In this discussion, Citra will explain statistics based on the orientation of the discussion, the techniques/methods used, the assumptions of the data/parameters, and the number of variables used.

By Purpose

RODA Statistics will explain statistics based on the goals you want to achieve. Statistics based on objectives are divided into two types: mathematical and applied. What is the difference between these two types of statistics? Let's see more of Citra's explanation.

Mathematical Statistics

This statistic does not focus on the application of data processing results and is more oriented towards statistical models and techniques used theoretically. This statistic is more about testing new statistical models or techniques that can be used.

Applied Statistics

In contrast to mathematical statistics, which focuses on theory, applied statistics focuses more on applying the methods used. So these statistics are used more in industry or other fields that can improve the performance of a process.

By Technique/ Method

Statistics based on methods are still divided into two types: descriptive and inferential. Citra will explain the difference between these two types of statistics.

Descriptive Statistics

The first statistic Citra will discuss based on his method is descriptive statistics. Statistics is closely related to data collection, processing, and presentation of data to provide information that can help its users.

Usually, this statistic uses data from a research group that will be used to explain the phenomena that occur in that group. The explanation of the group usually uses location size, variability measure, shape size, and graphic presentation in frequency distribution and histogram.

Inferential Statistics

The second discussion is inferential statistics. In contrast to descriptive statistics, which focuses on explaining data, inferential statistics focuses on the process of guessing the character of a group based on sample data. So this statistic looks at future predictions about a group.

Inferential statistics also determines where the sample data being tested comes from. If descriptive statistics is more about the condition of the sample data at that time, inferential statistics will find out where the sample data comes from along with estimates/forecasts and make decisions about the sample data.

Based on Data Terms/ Data Assumptions/ Parameters

Citra's next discussion is statistics based on data requirements or data assumptions made. This type of statistics is further divided into two types, namely parametric statistics and non-parametric statistics. Citra will explain the difference between these two types of statistics.

Parametric Statistics

Parametric statistics focuses on statistical testing methods strengthened by assumptions beforehand. Suppose you are going to take data from a normally distributed population. A normal distribution is an assumption that you make first, even though you don't know whether the population is normally distributed or not.

Most parametric statistics are used on interval and ratio scale data. Rarely are these statistics used on independent data without an ordered scale.

Non-Parametric Statistics

Non-parametric statistics focuses on testing statistical methods instead of parametric statistics, which uses few or no assumptions. This statistical method's data taken from a population is not bound to the statistical model.

If parametric statistics are used on interval and ratio scale data, then non-parametric statistics are used on ordinal and nominal scale data. So you can use various types of data freely with this method.

Based on the Number of Variables

The last type of statistical discussion that Citra will discuss is the type of statistics based on the number of variables. In this category of statistics, there are 3 types of statistics: univariate, bivariate, and multivariate.

Univariate Statistics

The first type of statistics that Citra will explain is univariate statistics. This statistic uses one variable in its analysis method because it makes summarising the data in a graphical form easier. If you are confused, the t-test, z-test, and normality tests are usually univariate statistics.

Bivariate Statistics

The second statistic that Citra will explain is bivariate statistics. Bivariate statistics use two variables in its research. Usually, this statistic explains a relationship or influence between variables. Examples such as correlation tests and regression tests.

Multivariate Statistics

The last statistic that Citra will discuss is multivariate statistics. Multivariate statistics use more than 2 variables in its research. This study focuses on deepening the phenomenon of many variables. One example is multiple regression, cluster, factor analysis, etc.

Terms in Basic Statistics

In statistics, there are also some terms that you must know. All these terms will come out every time you deal with statistics, from formulation to the interpretation of results. Citra will cover important terms such as data, population, sample, and variables. Let's see Citra's explanation below to understand it further.

Data

Earlier, Citra was talking about data. What is the data in statistics? Are you curious about the data? Let's see Citra's explanation of data in the world of statistics below.

Data in statistics is a measure of a variable you are looking for. For example, you want to research the age of 12-year-old children in village A. The data you are looking for is how many children aged 12 years in village A.

The data in statistics is divided into two types: qualitative data and quantitative data.

Qualitative Data

Qualitative data includes nominal and ordinal scale data. Nominal scale data include gender, blood type, hair colour, and region. While ordinal data, such as generation of birth, the answer is yes and no.

Quantitative Data

Quantitative data is divided into two, namely interval scale data and ratio scale data. Interval data shows tiered values, such as the temperature value of a room. While the value of the ratio shows an amount, for example, the value of a country's currency.

In addition to the type of data, it turns out that there are also several types of data presentation in the presentation. There are 3 types of data presentation in statistics, namely:

- Presentation in tabular form (usually used in data comparison)

- Presentation in the form of graphs/diagrams (used for more concise data visualization)

- Presentation in map form (Easier to read)

In statistics, the measurement of clustered data concentration is also carried out. Usually, the size of clustered data concentration is divided into 3, namely:

Mean (average)

Median (middle value)

Modus (most frequently occurring value)

In population data, there must be a distribution in it. Citra will tell you the types of distribution of group data in the population:

- Range (Difference between the largest and smallest data from a sample/population)

- Average Deviation (The average value of the difference between each data and the average value)

- Variety (Amount of data spread)

Standard Deviation

Population

In statistics, you will find quite a lot of data and each data you want to examine. The sum of the number of data that you want to examine is called the population. Units in the population can be referred to as units of analysis or units that will be analyzed. In addition to population, some people also refer to population as the universe.

Sample

For example, if you get a population consisting of thousands of data, how do you research that much data? Well, statistics usually use samples. This sample is a representation of the population both in terms of characteristics and quantity. For example, there are 5000 people. You just need to take 500 data because it already represents 5.000 data.

Variable

Citra will explain variables in statistics. Variables will generally tell you what you are going to examine. For example, we want to research catfish cultivators. The variable we want to examine is the monthly income of catfish cultivators. The variables that we have defined can be measured.

Measurement of this variable can be done by changing the variable into the form of a size scale. In statistics, the size of the scale is divided into four, namely ordinal, nominal, interval, and ratio. By determining the size of the scale, a variable can be measured.

Basic Statistical Formulas

Mean

The average is the sum of the number of data held divided by the amount.

Median

Modus

The modus is the value that frequently occurs in the data.

Information:

Mo is the modus

L is the lower edge of the class with the highest frequency

B1 and B2 are the frequency of the mode class minus the frequency of the nearest class before and after it

Range

Standard Deviation

"Learning basic statistics, especially the methods and formulas used will help you later when doing research. Basic knowledge of this material will be a guide for doing more complicated research."

Example of Basic Statistics Questions

The average scores for mathematics and physics in the Kunugigaoka class are 86.2 and 78.4. Nagisa got the same score for both subjects. If the average scores for math and physics without Nagisa's grades are 86.4 and 78.3, respectively, how many students are in the class?

a. 81

b. 27

c. 26

d. 24

e. 30

Discussion (B)

The average class value means the total number of students' scores in the class divided by the number of students. From the questions, we get the average math and physics scores, 86 and 80. Because Nagisa gets the same value for both subjects, we can make the problem above into a system of equations for two variables.

The value of Nagisa and x is the number of students in the class.

Analysis per choice

Choice A is wrong because the score is Nagisa's, not the number of students in the class.

Choice B is correct because if the equation is solved, we will get

So, there are 27 students in the class.

Choice C is wrong because it is the total number of students without Nagisa.

Option D is wrong because there is a miscalculation that should have happened.

Choice E is wrong because there is a miscalculation that should have happened.

So, the answer is B.

It's clear enough, is the explanation of RODA Statistics conveyed? If you have any questions, you can write them in the comment column.